Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1270 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.8282. Min Act: -0.0003

Data Index: 1421698 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7884. Min Act: -0.0003

Data Index: 1432221 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7842. Min Act: -0.0003

Data Index: 1590122 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6527. Min Act: -0.0003

Data Index: 1363913 (Python Code)

Max Activating Token Index: 838

Text #4

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5448. Min Act: -0.0003

Data Index: 1644776 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5116. Min Act: -0.0003

Data Index: 1474926 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5271. Min Act: -0.0003

Data Index: 1361962 (Python Code)

Max Activating Token Index: 412

Text #7

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.4857. Min Act: -0.0003

Data Index: 1470840 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5595. Min Act: -0.0003

Data Index: 1589860 (Python Code)

Max Activating Token Index: 518

Text #9

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5200. Min Act: -0.0003

Data Index: 1643976 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5139. Min Act: -0.0003

Data Index: 1468342 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.4972. Min Act: -0.0003

Data Index: 1394494 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.4999. Min Act: -0.0003

Data Index: 1416795 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.4949. Min Act: -0.0003

Data Index: 1496356 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5180. Min Act: -0.0003

Data Index: 1544452 (Python Code)

Max Activating Token Index: 497

Text #15

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.4819. Min Act: -0.0003

Data Index: 1549616 (Python Code)

Max Activating Token Index: 848

Text #16

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5025. Min Act: -0.0003

Data Index: 1527689 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5015. Min Act: -0.0003

Data Index: 1361134 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5186. Min Act: -0.0003

Data Index: 1623889 (Python Code)

Max Activating Token Index: 892

Text #19

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5324. Min Act: -0.0003

Data Index: 1480957 (Python Code)

Max Activating Token Index: 692